Object Detection in 20 Years: A Survey
Open accessThe DOI matches its Crossref record; 309 of the 309 references it cites were found in a registry or an index; 84 of the 192 sources its claims cite were checked for support.
Abstract
Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Over the past two decades, we have seen a rapid technological evolution of object detection and its profound impact on the entire computer vision field. If we consider today’s object detection technique as a revolution driven by deep learning, then, back in the 1990s, we would see the ingenious thinking and long-term perspective design of early computer vision. This article extensively reviews this fast-moving research field in the light of technical evolution, spanning over a quarter-century’s time (from the 1990s to 2022). A number of topics have been covered in this article, including the milestone detectors in history, detection datasets, metrics, fundamental building blocks of the detection system, speedup techniques, and recent state-of-the-art detection methods.
Overview
CoChat Summary
TL;DR
This survey reviews two decades of object detection research (1990s–2022), tracing the transition from handcrafted-feature detectors to deep-learning-based two-stage, one-stage, and transformer detectors. It organizes the field around milestone detectors, datasets and metrics, key building blocks (multi-scale detection, context, hard negative mining, loss functions, NMS), speed-up techniques, and recent advances.
Key findings
- The field splits into a "traditional object detection period (before 2014)" and a "deep learning based detection period (after 2014)"; RCNN raised VOC07 mAP from 33.7% (DPM-v5) to 58.5%, SPPNet reached VOC07 mAP=59.2% at >20× faster than R-CNN, Fast RCNN reached 70.0% mAP at >200× faster than R-CNN, and Faster RCNN reached COCO mAP@.5=42.7%, VOC07 mAP=73.2% at 17fps.
- One-stage detectors traded some accuracy for speed: YOLO ran at 155fps with VOC07 mAP=52.7% (enhanced version 45fps, 63.4%), SSD reached COCO mAP@.5=46.5% at 59fps, and RetinaNet's focal loss brought one-stage accuracy to COCO mAP@.5=59.1%.
- Keypoint- and transformer-based detectors pushed accuracy further: CornerNet COCO mAP@.5=57.8%, CenterNet 61.1%, and Deformable DETR 71.9% on MS-COCO; the paper notes the top-10 COCO detection methods are all transformer-based.
- Datasets scaled dramatically: VOC07 has 5k train images/12k objects, VOC12 11k/27k, MS-COCO-17 164k images and 897k annotated objects over 80 categories, and Open Images 1,910k images with 15,440k boxes over 600 categories. Evaluation moved from miss-rate vs. FPPW to FPPI, then to AP/mAP, with MS-COCO averaging over IoU thresholds 0.5–0.95.
Methods
- Design: a narrative literature survey spanning roughly a quarter-century (1990s to 2022), structured around technical evolution rather than a systematic/quantitative review protocol.
- Coverage: milestone detectors (VJ, HOG, DPM, RCNN, SPPNet, Fast/Faster RCNN, FPN, YOLO, SSD, RetinaNet, CornerNet, CenterNet, DETR), datasets and metrics, technical building blocks, speed-up techniques, and recent advances (rotation/scale robustness, backbones, localization, segmentation loss, adversarial training, weakly supervised detection, domain adaptation).
- Analysis: qualitative synthesis of reported detector accuracies and speeds, with figures/tables summarizing dataset statistics and accuracy trends; no new experiments are conducted.
Limitations
- The paper states no explicit limitations section; it frames its scope as presenting the evolution of technologies "while neglecting their technical specifics," and notes that the evolution order shown in figures is primarily to assist reader understanding and "may have temporal overlap."
- Evident from the text: as a survey it reports no original experiments or controlled benchmarks, so the cited mAP/speed figures come from the original papers and are not independently verified; the coverage is also selective (milestone detectors and selected recent advances) rather than exhaustive.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
55 Valid · 18 Not valid · 32 Not checked · 50 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“In the deep learning era, due to the increase of computing power, bootstrap was shortly discarded in object detection during 2014-2016 [16-20].”
What the sources say
- Not checked — no full text of the sourcecites [16] matched to “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation” (2014) source
- Disputedcites [17] matched to “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition” (2014) sourceExperimental — accuracy not yet measured
Section 4.1 (page unavailable) says the authors used standard hard negative mining, iterated once, to train their object-detection SVMs. That is contrary to citing this 2014 detector as evidence that bootstrapping had been discarded. The paper does not establish a 2014–2016 trend or attribute one to increased computing power. (LLM, conf=0.78)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites [18] matched to “Fast R-CNN” (2015) source
- Partly supportedcites [19] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 (p. 10) says Fast R-CNN abandoned the SVM step that, in SPPnet, used hard-negative mining. This supports a narrower change in one detection system, but not the claim that bootstrapping was discarded across object detection during 2014–2016 or that increased computing power caused the change. (LLM, conf=0.83)
- Could not verifycites [20] matched to “You Only Look Once: Unified, Real-Time Object Detection” (2016) sourceExperimental — accuracy not yet measured
The Introduction (p. 1) contrasts YOLO with earlier detection methods, and Training (p. 3) describes how YOLO is trained. Neither passage addresses whether bootstrapping was discarded in object detection during 2014–2016 or attributes such a change to increased computing power; searches for bootstrapping and hard-negative mining found no passage that does. (LLM, conf=0.72)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Faster RCNN is the first near-realtime deep learning detector (COCO mAP@.5=42.7%, VOC07 mAP=73.2%, 17fps with ZF-Net [48]).”
What the sources say
- Partly supportedcites [19] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 reports 42.7% COCO mAP@0.5; Section 4.1 reports 73.2% VOC 2007 mAP and 17 fps with ZF-Net. These are results from different model configurations: the 73.2% VOC result uses VGG-16, not ZF-Net. The paper describes Faster R-CNN as a fast detector but does not establish that it was the first near-real-time deep-learning detector. (LLM, conf=0.88)
- Partly supportedcites [47] matched to “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (2017) sourceExperimental — accuracy not yet measured
Section 4.2 reports 42.7% COCO mAP@0.5, and Section 4.1 reports 73.2% VOC 2007 mAP and 17 fps with ZF-Net. The accuracy figures are from VGG-16 experiments, not the 17-fps ZF-Net configuration. The paper describes Faster R-CNN as a fast detector but does not establish that it was the first near-real-time deep-learning detector. (LLM, conf=0.88)
- Partly supportedcites [48] matched to “Visualizing and understanding convolutional networks” (2014) sourceExperimental — accuracy not yet measured
Section 3 (p. 4) describes the authors’ convolutional-network architecture, supporting the citation as an identification of the ZF-Net backbone. The paper does not report Faster R-CNN’s near-real-time status, COCO or VOC07 mAP, or 17-fps speed, so it does not support those performance claims. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In the case of sliding window based detectors, the imbalance between backgrounds and objects could be as extreme as 10 7 :1 [71].”
What the sources say
- Partly supportedcites [71] matched to “What Makes for Effective Detection Proposals?” (2016) sourceExperimental — accuracy not yet measured
The Introduction (p. 1) says sliding-window detection can search 10^6–10^7 windows per image. It does not say that 10^7 of those windows are backgrounds for each object, so it does not establish the claimed 10^7:1 imbalance. (LLM, conf=0.88)
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“It achieves state-of-the-art performance on MSCOCO dataset (COCO mAP@.5=71.9%).”
What the sources say
- Supportedcites [43] Zhu, 2020, Deformable DETR: Deformable transformers for end-to-end object detection, arXiv:2010.04159 source
Section 5.3 (pp. 8–9) compares Deformable DETR with state-of-the-art methods on COCO. Its table reports an AP50 of 71.9 for the ResNeXt-101 + DCN configuration with test-time augmentation; the accompanying text reports 52.3 overall AP for that configuration. (LLM, conf=0.91)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Using FPN in a basic Faster R-CNN system, it achieves state-of-the-art single model detection results on the COCO dataset without bells and whistles (COCO mAP@.5=59.1%).”
What the sources say
- Supportedcites [24] matched to “Feature Pyramid Networks for Object Detection” (2017) source
The Introduction describes a state-of-the-art single-model COCO result using FPN with a basic Faster R-CNN detector, without bells and whistles. Section 5.2.3 reports AP@0.5 of 59.1 on COCO test-dev and says the single-model entry surpassed competition winners. Page numbers are not provided in the copy. (LLM, conf=0.94)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
50 more claims · 21 with their cited sources checked
Create a free account to see all 155 claims and to verify the 3 references still open.
- It may state two separate claims as one. 40
- Probably not a substantial claim. 83
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“From navigating through occlusions to efficiently managing scale variations and fine-grained object detection scenarios [9], YOLO faces a myriad of obstacles.”
From YOLOv1 to v8: Unveiling Each Variant–A Comprehensive Review of YOLO (2024) · cites this paper as [9]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The speed-up techniques in object detection can be divided into three levels of groups: speed up of 'detection pipeline', 'detector backbone', and 'numerical computation'. , as shown in Fig. 9. Refer to [123] for a more detailed version.”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [123]
The cited source says what the claim attributes to it.
In the citing paper
“The few surveys that mention both object detection and model compression [11] focus on the acceleration of”
From A survey of model compression strategies for object detection (2023) · cites this paper as [11]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“In addition to that, most of the reviews in related fields review the object detection model and model compression technology separately, and there is a lack of comprehensive reviews for both.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [11]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ II. OBJECT DETECTION IN 20 YEARS
“Fig. 2: A road map of object detection. Milestone detectors in this figure: VJ Det. [10, 11], HOG Det. [12], DPM [1315], RCNN [16], SPPNet [17], Fast RCNN [18], Faster RCNN [19], YOLO [20-22], SSD [23], FPN [24], Retina-Net [25], CornerNet [26], CenterNet [27], DETR [28].”
§ Object detection accuracy improvements
“CenterNet: X. Zhou et al proposed CenterNet [40] in 2019.”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 4×
“As the accuracy of a detector depends heavily on its feature extraction networks, in this paper, we refer to the backbone networks, e.g. the ResNet and VGG, as the “engine” of a detector.”
InfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 5×
“In 2012, the world saw the rebirth of convolutional neural networks (CNNs) [35].”
InfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 10×
“The main idea of multi-reference detection [19, 22, 23, 41, 47, 51] is to first define a set of references (a.”
InfluentialFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“It contains a detection challenge using ImageNet images [61].”
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 3×
“Some well-known detection models of the early time: (a) Eigenfaces [95], (b) Shared weight networks [96], (c) Space displacement networks (Lenet-5) [97], (d) Haar wavelets of VJ detector [10].”
BackgroundMethodDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 1×
“HOG can be considered as an important improvement of the scale-invariant feature transform [33, 34] and shape contexts [35] of its time.”
BackgroundYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 9×
“L2 loss is prevalent in early research [16], [20], [51], but it is highly affected by outliers and prone to gradient explosion.”
InfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Research works printed but not linked: 9
- 10.5555/3045118.3045336 · doi:10.5555/3045118.3045336
- Girshick, 2023, Discriminatively Trained Deformable Part Models, Release 5
- 10.1109/TPAMI.2016.2577031 · DOI · Paper page
- Krasin, 2017, OpenImages: A Public Dataset for Large-Scale Multi-Label and Multi-Class Image Classification
- Alexe, What is an object, 73
- Müller, When does label smoothing help, 32, 1
- 10.1109/CVPR.2016.308 · DOI · Paper page
- 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
- 10.1109/ICCV.2017.244 · DOI · Paper page
Cited by
Items 2,401–2,500 of 3,144
Prioritizing Test Cases Through Dual-Uncertainty Evaluating for Road Disease Detection System
Niu, C., Liu, H., Li, A., Xiao, T., Zhimin, R., Xu, L., & Ge, Y. (2024) · Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec65559.2024.00041
“This belongs to the object detection task of computer vision [23], and its core lies in training the model by using a large number of annotated images, where the annotated information includes the object position and category in the image, so that the model can accurately detect these objects on…”
Comparative Performance of Object Detection Algorithms Under Low Illumination Conditions
Hossain, M. J., Rahman, S., Monir, M. F., et al. (2025) · Proceedings of IEEE Southeastcon · doi:10.1109/southeastcon56624.2025.10971492
“Zhou et al. (2023) proposed a classical and modern methods for better detecting reliability [10].”
Assessing the applicability of 3D time-of-flight cameras for digital monitoring of cow exterior
Yurochka, S. S., PAVKIN, D. Y., Khakimov, A. R., et al. (2025) · Agrarian science · doi:10.32634/0869-8155-2025-393-04-145-152
A Multi-Scale Object Detection Model Based on Differentiable Architecture SearchPreprint
Xue, Y., Luo, P., Tan, Y., & Zhen, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5231594
Improved Pose Estimation Network Based on Spatial Registration Model
Liu, Z., Dong, Z., Yin, X. L., et al. (2024) · Journal of engineering system. · doi:10.62517/jes.202402307
Combining Instance Segmentation and Background Subtraction Models for Small Object Detection
Dhammatorn, W., Ito, S., Kaneko, N., & Sumi, K. (2025) · International Journal of Automation Technology · doi:10.20965/ijat.2025.p0237
Design and Analysis of Data Synthesis Pipeline for Assembly Detection with Domain Randomization
Sun, C., Kinnell, P. K., Guo, C., et al. (2025) · International Conference on Automation, Robotics and Applications · doi:10.1109/icara64554.2025.10977644
“This is essential for models handling diverse real-world scenarios like occluded or small objects, as noted in recent benchmarks [9].”
LMAI2C: Low memory access Im2col method for CNN inference
Li, M., Chen, Z., Hong, J., Zhang, Y., Hao, X., Chen, M., & Ni, M. (2025) · IEICE Electronics Express · doi:10.1587/elex.22.20250246
Road Damage Target Detection Using Attention Mechanism and Convolutional Dense Scale Feature Fusion
Wang, G., Zhang, X., Wang, R., Wang, K., & Li, Q. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-4963-1_47
Application of Deep Learning Techniques for Accurate Fish Segmentation
Slimi, R., Youssef, W. E. H., Khriji, L., & Nadir, Z. (2025) · International Conference for Artificial Intelligence, Applications, Innovation and Ethics (AI2E) · doi:10.1109/ai2e64943.2025.10983008
“In contrast, one-stage detectors prioritize speed but may struggle with smaller objects; however, recent iterations like YOLOv8 have made notable strides in improving these limitations [8] [9].”
Qian, L., Sun, S., & Long, S. (2025) · Electronics · doi:10.3390/electronics14102033
Shape-Aware Dynamic Alignment Network for Oriented Object Detection in Aerial Images
Zhu, L., Jing, D., Lu, B., Zheng, D., Ren, S., & Chen, Z. (2025) · Symmetry · doi:10.3390/sym17050779 · Cited by 4
Bach, N. L. T., & Mutaher, H. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-2647-4.ch020
Scene Graph Generation Approach with Integrated Environmental Contextual Information
Sun, Y., Zhu, Y., Tao, Y., & Li, B. (2025) · Asia Conference on Algorithms, Computing and Machine Learning (CACML) · doi:10.1109/cacml64929.2025.11010975
“Object detection serves as a cornerstone in the realm of computer vision[11].”
YOLOv8 for Robust Traffic Object Instance Segmentation using Image Quality Assessment
Deepthi shree, A. M., & Brindha, M. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.291
Tracking Virtual Meetings in the Wild: Re-identification in Multi-participant Virtual Meetings
Perl, O., Leshem, I., Franko, U., & Goldman, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91581-9_13
MCF-Net: Personnel and machinery detection model for complex downhole drilling environments
Jin, Z., & Li, H. (2025) · PLoS ONE · doi:10.1371/journal.pone.0320653 · Cited by 1
“Target detection is a fundamental task of computer vision, which has been widely used in various real-world scenarios [14], such as autonomous driving, robot vision, video surveillance, etc.”
Datta, J., Sarwar, F. A., Rabbi, R., Saha, P., Alam, M. G. R., Uddin, J., & Zereen, A. N. (2025) · International Conference on Electrical, Computer and Communication Engineering · doi:10.1109/ecce64574.2025.11013059
“In recent years, Artificial Neural Networks (ANNs) have shown extraordinary performance in tasks for example object detection and image classification, but require high power and computational resources [1]–[3].”
Enhancing Space Debris Detection and Classification Using Optimized YOLO Variants
Nawar, S., & Azhar, T. (2025) · International Conference on Electrical, Computer and Communication Engineering · doi:10.1109/ecce64574.2025.11013138
Small Object Detection of Human Face Melasma Based on Improved YOLOv5s
Bi, J., Pan, X., Feng, Y., et al. (2025) · International Conference on Software Engineering and Computer Science (CSECS) · doi:10.1109/csecs64665.2025.11009611
“…used convolutional neural network (CNN) and YOLO algorithms have strong generalisation ability and can accurately identify and locate melasma [5], e.g., in 2022 Goel et al. based on recurrent neural network to enhance the precision of melasma detection [6] ; in 2023 Liu et al. proposed a…”
Jeong, I., Kim, J., Lim, S. P., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5275805
ERF-NAS: Efficient Receptive Field-Based Zero-Shot NAS for Object Detection
Yu, X., Yin, R., Lin, Z.-H., & Wang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91979-4_17
OA-iTNet: object attention inverted transformer network for low-light-level image denoising
Wang, F., Yin, L., Qin, Y., Gao, X., Zhou, H. M., & Deng, Y. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01859-6 · Cited by 1
“Whether it is image classification [4, 5], image segmentation [6, 7], object detection [8, 9], object tracking [10, 11], noise-free, high-quality images are the basic requirements for excelling in these advanced computer vision tasks.”
AIPNet: Action-Instance Progressive Learning Network for Instrument-Tissue Interaction Detection
Lin, W., Hu, Y., Hao, L., et al. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3575791
“In the early stages, two-stage CNN-based object detection models, which frame detection as a “coarse-to-fine” process, dominated the field [14].”
Resource-Efficient Multiview Perception: Integrating Semantic Masking with Masked Autoencoders
Dakic, K., Thilakarathna, K., Calheiros, R. N., & Lim, T. J. (2025) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom64205.2025.00034 · Cited by 7
“In this work, we presented a novel approach for communication-efficient distributed multiview detection and tracking using masked autoencoders.”
A Weak and Small Target Detection Algorithm Based on the View of UAV
Pan, W., Xu, B., Zhang, C. H., et al. (2025) · International Conference on Advanced Algorithms and Control Engineering (ICAACE) · doi:10.1109/icaace65325.2025.11018885
“Many scholars have done a lot of research to improve the detection performance [1][2][3][4] .”
CSD-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Images
Wei, Y., Tao, J., Wu, W., Yuan, D., Hou, S., & Cheng, Y. (2024) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait63902.2024.11022083
“Unmanned Aerial Vehicle (UAV) plays an increasingly crucial role in the intelligence process within the realm of object detection [1]. which is because of its small size, fast speed and flexible detection.”
Platypus Detection Through Deep Learning
Shen, M., & Sinnott, R. (2024) · International Conference on Sustainable Technology and Engineering (i-COSTE) · doi:10.1109/i-coste63786.2024.11024807
“The object detection techniques used in this study are anchor-based methods which include both one-stage and two-stage detection algorithms [39], [44].”
A Low-Complexity YOLOv8s-Based Model for Environment Perception in Power Maintenance Guided Vehicles
Gan, Z., Li, J., Wu, P., He, D., Liao, L., Zeng, N., Xiong, B., Guo, F., & Bai, Y. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3578634
“The specific definitions of these metrics, along with their corresponding formulas [44], are presented as follows :”
Prompt-Driven Approach for Cattle Image Segmentation Based on SAM
Bello, R.-W., Owolawi, P. A., Tu, C.-C., & Wyk, E. V. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-92605-1_5
Multi-View Object Recognition and Pose Sequence Estimation Using HMMs
Núñez, L., Savage, J., Moctezuma, M., Contreras, L., Negrete, M., & Okada, H. (2025) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2025.p0579
The Structrual Tuning Training Strategies for Few-Shot UAV Detection Based on YOLO
Rao, J., Zhang, J., Bao, Q., & Peng, Z. (2025) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda64898.2025.11030485
“In the development of deep learning neural networks, a variety of object detection[23-25] algorithms have emerged.”
Recent Trends in AI-Driven Human Detection Tactics
Ansari, M. A., Anwar, K., Mewada, A., & Zafar, A. (2025) · BENTHAM SCIENCE PUBLISHERS eBooks · doi:10.2174/9789815322583125010007
Kim, J., Jung, Y., Parajuli, S., Shrestha, S., Park, J., Cho, G., & Lee, J. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500178 · Cited by 1
Enhanced YOLOv5s Model for Improved Multi-Sized Object Detection in Road Scenes
Sangavi, S., & Gunaseelan, D. (2025) · IEEE Access · doi:10.1109/access.2025.3582136
“As a result, single-stage detectors have gained prominence for their ability to process images faster by predicting object locations and classes in a single pass, making them more efficient for real-time use [3].”
SAMatch: training-free object detection for HMI screens
Kannan, K., Jaisankar, V., Pillai, A., & Tripathi, R. (2025) · Discover Data · doi:10.1007/s44248-025-00038-2
“Contrary to conventional scenarios [1], object detection in HMI screens presents unexpected challenges owing to diverse objects and limited data.”
Lin, Y.-C., Yu, T.-T., Yang, Y.-E., et al. (2025) · Remote Sensing · doi:10.3390/rs17132131
Domain Randomization for Object Detection: A Survey
Fan, J., Xie, Y., & Li, Z. (2025) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1109/aemcse65292.2025.11042418 · Cited by 2
“It goes beyond simple image classification by recognizing multiple objects within a scene and providing their bounding boxes, the coordinates that define their position and size [1].”
Separable and Flexible Classification on Pseudo-Features for Few-Shot Class-Incremental Learning
Yang, Y., Jin, L., Zhang, S., & Tong, C. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733431 · Cited by 1
“These tasks, once reliant on manual feature engineering[52], are now effectively addressed through deep learning, significantly impacting various applications.”
Wu, F., Li, M., Zhou, C., et al. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116038
Robust and Automatic Visual Guidance Framework for Component Localization on Printed Circuit Boards
Zheng, Y., Chen, Z., Wu, L., et al. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3576837
“Object detection is an active research area in the field of computer vision, for example, general object detection algorithms [8], domain-specific object detection [14], [26], [27], [28], and small object detection [22], [23], [24], [25], which has been developed greatly over the past two decades.”
Cutting-Edge Vision: Object Detection Mastery with YOLOv5
Navedha Evanjalin, R., Mohaideen Pitchai, K., & Garpahaganesh, R. (2025) · International Conference on Innovative Trends in Information Technology (ICITIIT) · doi:10.1109/icitiit64777.2025.11040903
Automated Identification and Numbering of Brick in Orthoimages of Ancient City Walls with Settlement
Zou, Z., Zhao, X., Zhao, P., Qi, F., Li, J., & Jie, Y. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6672
Self-citationEvaluating Real-Time Object Detection Models for Autonomous Vehicular Vision applications
Bahri, S., & Mouftah, H. T. (2025) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc65282.2025.11059704
“Object detection models by and large generate output that embraces object classes, their relevant locations in the image, and a confidence score, extending a comprehensive synopsis of the scene [20].”
Microscopic Detection Approach of Chinese Herbal Medicine Base on YOLOv8
Mo, J., Peng, Z., Li, W., et al. (2024) · International Conference on Ubiquitous Computing and Communications (IUCC) · doi:10.1109/iucc65928.2024.00048
“…and small sample sizes has emerged as a key challenge in verifying the authenticity of TCM. Owing to the rapid advancement of deep learning technologies, considerable progress has been achieved in the domain of object detection, encompassing both one-stage and two-stage model architectures [9].”
Quality Detection Model of Nutmeg (Myristica Fragrans Houtt) Using You Only Look Once (YOLO)
Pacheco, M. S. D. R., Hadiyanto, H., & Sanjaya, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-3250-3_54
Facial Expressions Detections Model Using YOLOv5 Trained with Custom Images
Ishtiaq, H. M., Siddique, A., Fayez, Husain, M. Z., Hasan, M. Z., & Nosheen, S. (2024) · Recent Advances in Sustainable Engineering and Future Technologies (RASEFT) · doi:10.1109/raseft61414.2024.00025
YOLO-KAN: Exploring the Adaptability of Kolmogorov-Arnold Networks in the YOLO Model
Zhao, X., Lee, J., & Amjad, T. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00144
“Computer vision is one of the major application areas of Artificial Intelligence, and object detection is currently one of the key research focuses within computer vision [1].”
Active Object Detection Using a Novel Network and Partial Prior Information
Wang, J., Zhu, F., Wang, Q., & Zhao, P. (2025) · Expert Systems · doi:10.1111/exsy.70095
Adaptive Retraining Techniques for Foreign Object Detection in Industrial Environments
Purayil, S. V., Popa, M. C., Winands, M. H. M., & Mihaľák, M. (2025) · doi:10.1109/cism64958.2025.11060857
“Active learning has been used in the conventional object detection tasks where the main objective is to detect all objects in an image of a complex scene, typically containing many objects [9], [25].”
Guerra, B. M. V., Sozzi, S., Soldi, R., et al. (2025) · doi:10.1109/memea65319.2025.11068105
“Several architectures have emerged as effective solutions, including Region-based CNNs (R-CNN), Faster R-CNN, and Mask R-CNN [11], as well as lightweight models such as MobileNet and SqueezeDet [12].”
Visual-Based Dual-Branch Structure for Bird’s-Eye-View Object Detection
李, 朝. (2025) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2025.144080
ABDet: Adaptive Feature Enhancement and Boundary Alignment Loss for Object Detection
Wen, J., Zhang, T., Li, J., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9794-6_16
Li, N., Lv, Y., & Li, F. (2025) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs65393.2025.11069698
“With advancements in science and technology, various imaging techniques have become increasingly mature[4][5].”
FOADA: Toward Robust Open-World Mobile App Fingerprinting
Gong, J., Meng, G., Cai, W., Liang, S., Wang, T., & Chang, E. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3589008 · Cited by 1
“Object Detection (OD) [17], [22], a rapidly developing topic in computer vision, leads us to new insights for AF attacks.”
Investigating the Transferability of TOG Adversarial Attacks in YOLO Models in the Maritime Domain
Manasut, P., Ibtasham, M. S., Yaradanakul, Z., Azimi, S., Lafond, S., & Iancu, B. (2025) · IEEE Access · doi:10.1109/access.2025.3589512
Wang, Z., Peng, Y., Zhang, X., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5353428
Logomask: Robust Web Logo Detection by Hypergraph-Induced Text MaskingPreprint
Hu, C., Li, S., Liu, R., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5353533
Hao, Z., Yang, H., & Liu, T. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9961-2_2
Dual-coded underwater image enhancement utilizing multi-color space and multi-scale synergy
Wei, D., Yuan, G., & Qu, Y. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04507-8 · Cited by 1
“These degraded images can hinder various computer vision tasks, including target detection [2], wide-field underwater vision reconstruction [3], and scene understanding [4].”
Underwater Target Detection Improved Algorithm Based on Deep Learning
Ma, C., Sun, Q., & Jiang, Z. (2025) · Signals and communication technology · doi:10.1007/978-3-031-89994-2_1
Raza, S. M., Abidi, S. M. H., Masuduzzaman, M., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5363643
Park, J., Koh, J. W., Yoon, T., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5364240
Pedestrian detection algorithm based on computer vision
Li, X., & Ruan, H. (2025) · IEEE International Conference on Electronic Technology, Communication and Information (ICETCI) · doi:10.1109/icetci64844.2025.11084137
“Object detection technology focuses on identifying and locating specific instances in digital images, such as pedestrians, animals, etc., and providing this information to other computer applications [6].”
Lai, Z., Guo, X., Kong, H., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9908-7_26
GL-Unet: Global-Local Attention Based Image Segmentation Algorithm for Transmission Line Defects
Wang, J., Ding, X., Tian, K., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9869-1_11
Luo, S., & Lu, B. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251361850
Early Data Fusion in Low-Light Vision for YOLO
Niedziółka, P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-01773-4_8
Improved DETR for Pedestrian Detection from the Perspective of UAV
Wang, Z., Jin, H., Xue, C., Zhang, T., & Chen, L. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-7178-6_13
Peng, Y., Yang, L., Yang, H., Wu, T. H., Li, X., & Zhang, J. (2025) · Food Control · doi:10.1016/j.foodcont.2025.111580
Enhancing Acute Lymphoblastic Leukemia Classification and Detection Using Deep Learning
Kumar, A., & Raimond, K. (2025) · doi:10.1109/icc-robins64345.2025.11086223
“Such a task is pivotal to various applications, including image retrieval, video surveillance, autonomous driving, robot vision, and medical image diagnoses [21].”
Image Caption Generation Evaluation Based on XceptionNet, VGGNet, and ResNet
Reddy, B. S., Sharma, G., & Eapen, N. G. (2025) · Asset analytics · doi:10.1007/978-981-96-7556-2_15
Human-Centered Computer Vision for Urban Sensing
Yin, H., & Zhang, F. (2025) · Springer geography · doi:10.1007/978-3-031-87421-5_6 · Cited by 1
DCHT-Net: Medical Object Detection Based on Dynamic Deep Circular Hough Transform
Liu, W., Lu, W., Huang, Z., Huang, B., & Chen, F. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9884-4_43
Human-Machine Proximity and Warning System for Industrial Safety
Bilsel, T. E., Çolak, M., Akman, N. P., & Berkol, A. (2025) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai65401.2025.11095460
“In recent years, the success of models like YOLO (You Only Look Once), SSD (Single Shot Detector), and Faster R-CNN (Faster Region-Convolutional Neural Network), which leverage these techniques, has significantly advanced object detection in terms of both speed and accuracy [1].”
InfluentialLi, X., Jia, Y., Yu, J., & He, F. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010249
Gao, Z., Dong, Z., Zhang, X., et al. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090931
“State-of-the-art computer vision techniques [5] exhibit residual errors that propagate through subsequent control layers, causing trajectory deviations and compromising operational safety [6].”
OC-DETR: DETR with Orthogonal Channel Attention and CSPO-Fusion for Component Detection of TEDS
Song, C., Peng, G., Wang, C., et al. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11090495
“At present, object detection methods based on deep learning are mainly divided into two-stage target detection models represented by the fast RCNN series and single-stage target detection models represented by the YOLO and DETR series[5].”
Horihata, T., Yoshida, S., & Muneyasu, M. (2025) · IEEE Access · doi:10.1109/access.2025.3596221
“Deep neural networks (DNNs) have revolutionized computer vision tasks [1], [2], [3]; however, they rely on large, representative datasets for optimal performance.”
Confidence-Based Zero-Shot Out-of-Distribution Detection Via Self-LearningPreprint
Todescato, M. V., & Carbonera, J. L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5384585
Evaluating Real-Time Object Detection Models for Autonomous Vehicle Vision
Bahri, S., & Mouftah, H. T. (2025) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot65859.2025.11105268
“It leverages EfficientNet, a favorably efficient image classification model, and incorporates the BiFPN (Bidirectional Feature Pyramid Network) for efficient multi-scale feature fusion [13].”
BIOSKOP: AI based Microscope Design for Biological Survey and Object Analysis
Uludağ, K., Akhan, B., Değirmenci, E., et al. (2025) · International Symposium on Innovative Approaches in Smart Technologies (ISAS) · doi:10.1109/isas66241.2025.11101788
Jeong, J., kim, J., Park, J., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5388901
Stateless distributed Stein variational gradient descent method for Bayesian federated learning
Li, G., Gan, J., Wang, C., & Peng, S. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131198
Visual Slam in the Heterogeneous Intelligence Era: A SurveyPreprint
Su, S., He, X., Meng, X., Zhang, Y., Yin, W., Mo, L., & Yu, F. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5383002
Wang, J., Su, J., & Sun, Y. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084583
A path aggregation network with deformable convolution for visual object detection
Rao, C. S., Hu, Z., Zhao, Q., et al. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3083
Introducing attention shortcuts in convolutional neural networks
Erroz, D., & Galar, M. (2025) · Electronic Research Archive · doi:10.3934/era.2025215
Utility-Aware Resource Allocation for Multigroup Collaborative Perception System
Yang, Y., Yuan, Q., Li, Y., Luo, G., Fu, X., Liu, J., & Li, J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3599528 · Cited by 2
“Modern object detection networks, such as Yolo and Faster R-CNN can extract features at multiple granularity [32], [33], [34], [35], [36], and sharing finer granularity collaborative features between pairs provides richer perception information but incurs a higher communication burden due to the…”
Auto Object Detection and Tracking Using Trajectory Matching in Test Range Scenarios
Swain, D., Chauhan, M. S., Dey, P., et al. (2025) · International Conference on Range Technology (ICORT) · doi:10.1109/icort64008.2025.11115327
“Target classification in images has recently made great advancements due to deep learning algorithms[4][5].”
Bi-granularity balance learning for long-tailed image classification
Ren, N., Li, X., Wu, Y., et al. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104469
Exploring Object Detection Learning: A Teaching Guide Through Educational Online Tutorials
Fernandes, T., Silva, T., VAZ, J. F. N., et al. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-02672-9_9
MCPD‐YOLOv3: A Novel Lightweight Detection Model for Surgical Instruments in Laparoscopic Images
Li, Y., li, C., Zhang, K., Miao, Y., Shi, W., & Jiang, Z. (2025) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.70104
AI‐ and Image‐Based Analysis of Emulsification Processes: Opportunities and Challenges
Burke, I., Derkum, S., Olusanya, T. O. O., & Kockmann, N. (2025) · Chemie Ingenieur Technik · doi:10.1002/cite.70018
Object Detection on Complex Architectural Floor Plans with Efficient Attention Mechanisms
Xu, Z., Jha, N., Mehadi, S., Maity, S. P., & Mandal, M. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4273-1_8
Uncertainty-Guided Enhancement on Driving Perception System Via Foundation Models
Yang, Y., Hu, Y., Ye, M., Zhang, Z., Lu, Z., Xu, Y., Topcu, U., & Snyder, B. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127651 · Cited by 3
“Multimodal foundation models [1], [2], [3], with the ability to process texts and images, have demonstrated impressive capabilities on perception tasks such as object detection [4], [5], [6], motion prediction [7], [8], image QA and captioning [9], [4], and video understanding [10], [11], [12].”
YOLO-ACNet: A Lightweight Multiscale Object Detection Network for Autonomous Driving
Xin, H., & Deng, L. (2025) · International Symposium on Robotics, Artificial Intelligence and Information Engineering (RAIIE) · doi:10.1109/raiie65740.2025.11140258
“Object detection, a cornerstone of computer vision research [1], addresses the dual objectives of simultaneous object recognition and spatial localization, typically achieved through bounding box regression or segmentation mask prediction.”
Task-Oriented Pre-Training for Drivable Area Detection
Ma, F., Zhao, G., Qi, W., Liu, M., & Ma, J. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127457 · Cited by 1
“This pre-training and fine-tuning paradigm has led to advanced improvements in many computer vision tasks, including object image classification [13], object detection [14], and semantic segmentation [15].”
Babu, A. V., J, A. K. M., Damodaran, S., James, R. K., & Warrier, T. S. (2025) · International Conference on Advancements in Power, Communication and Intelligent Systems (APCI) · doi:10.1109/apci65531.2025.11136868 · Cited by 1
“Neural Networks (CNNs) [2], have revolutionized object detection by significantly enhancing accuracy and efficiency.”
Research on Airport Runway Detection Method based on Improved YOLOv11
Su, X., Xu, S., Ren, Y., et al. (2025) · International Conference on Information Science, Computer Technology and Transportation (ISCTT) · doi:10.1109/isctt66403.2025.11137975
“Among them, the YOLO (You Only Look Once) series is widely used in practical deployments due to its end-to-end structure and high detection speed [3] .”
Metadata
- Authors
- Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J.
- Affiliations
- Shanghai Artificial Intelligence Laboratory (CN)
- Carleton University (CA)
- Alibaba Group (China) (CN)
- Venue
- Proceedings of the IEEE
- Published
- 2023-03
- Volume
- 111
- Issue
- 3
- Pages
- 257-276
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W4320002812
- Cited by
- 3,689
- References
- 272
- Citations by year
- 2026: 610 · 2025: 1013 · 2024: 940 · 2023: 541
- FWCI
- 280.65
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62125102)
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, evaluation metrics, deep learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.